A Python package to use an AI assistant for historical analysis
Project description
This is dbnl_bear, a python package to make it easier to use AI for reading assistance in historical analaysis.
The "bear" part of the package name is inspired by a passage from Alex Komoroske's Bits and Bobs:
"LLMs are like a trained circus bear that can make you porridge in your kitchen. It's a miracle that it's able to do it at all, but watch out because no matter how well they can act like a human on some tasks they're still a wild animal. They might ransack your kitchen, and they could kill you, accidentally or intentionally. Just because it can talk like a human doesn't mean it deserves the responsibility of a human!" (editorial changes by AvD)
The package is available on PyPi. However, currently, it's not perfect, and should be used with some caution.
The goal of the package is to make it easier for historians to use AI in their research. It will assist in parsing texts, sending them to the OpenAI API, and viewing the results.
See the notebook for info on how to use this.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file dbnl_bear-0.2.tar.gz.
File metadata
- Download URL: dbnl_bear-0.2.tar.gz
- Upload date:
- Size: 6.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a152e4c15f3e696310e8505790b675b8932fe00413c0548f4220c5af930b1a82
|
|
| MD5 |
35d9a597bbd0688ff17e67b99c1fe245
|
|
| BLAKE2b-256 |
46a027279032847c2c4f8168dd0e8999a201a9fe2025c921370bdcb6cac1c65a
|
File details
Details for the file dbnl_bear-0.2-py3-none-any.whl.
File metadata
- Download URL: dbnl_bear-0.2-py3-none-any.whl
- Upload date:
- Size: 6.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.11.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c20b7a4fc59b1f35907202d4e020f33642e9e7bcad68b3ea382adf538cf4ebd6
|
|
| MD5 |
cbd2c186ef36a81384a15a291099d85a
|
|
| BLAKE2b-256 |
7c2b8b45861418a56bfad870b64dcad5690c4cdd3d72762d491547f1008a4595
|